Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1595611 (Python Code)

Max Activating Token Index: 988

Text #1

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1463757 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1492182 (Python Code)

Max Activating Token Index: 387

Text #3

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1449475 (Python Code)

Max Activating Token Index: 991

Text #4

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1614369 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1461616 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1375848 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1359874 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1580265 (Python Code)

Max Activating Token Index: 993

Text #9

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1611053 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1641070 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1579173 (Python Code)

Max Activating Token Index: 153

Text #12

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1655731 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1641530 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1571433 (Python Code)

Max Activating Token Index: 712

Text #15

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1870. Min Act: -0.0000

Data Index: 1528824 (Python Code)

Max Activating Token Index: 821

Text #16

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1364365 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1549682 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1502773 (Python Code)

Max Activating Token Index: 434

Text #19

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1388764 (Python Code)

Max Activating Token Index: 55